[bigyabai]

I don't believe it. MLX is a proprietary model format and usually the last to get supported on Huggingface. Given that most iOS users aren't selecting their own models, I genuinely don't think your conjecture adds up. The majority of people are likely using safetensors and GGUF, not MLX.

If you had a source to cite then it would remove all doubt pretty quickly here. But your assumptions don't seem to align with how iOS users actually use their phone.

[slashdave]

I didn't know the entire ML world is defined by what appears in HuggingFace

[bigyabai]

I never attributed the entire ML world to Huggingface. I am using it to illustrate a correlation.

[llm_nerd]

Cite a source? That CoreML models are prolific on Apple platforms? That Apple devices are prolific? Search for it yourself.

You seem set on MLX and apparently on your narrow view of what models are. This discussion was about ANE vs "tensor" units on the GPU, and someone happened to mention MLX in that context. I clarified the role of MLX, but that from an inference perspective most deployments are CoreML, which will automatically use ANE if the model or some subset fits (which is actually fairly rare as it's a very limited -- albeit speedy and power efficient -- bit of hardware). These are basic facts.

>how iOS users actually use their phone.

What does this even mean? Do you think I mean people are running Qwen3-Embedding-4B in pytorch on their device or something? Loads of apps, including mobile games, have models in them now. This is not rare, and most users are blissfully unaware.

[kanaffa12345]

> That CoreML models are prolific on Apple platforms? That Apple devices are prolific?

correct and non-controversial

> An enormous number of people and products [use CoreML on Apple platforms]

non-sequitur

EDIT: i see people are not aware of

https://en.wikipedia.org/wiki/Simpson%27s_paradox